High Discrimination Ability Research Articles

High expression of RHOF is an effective diagnostic marker and a potential prognostic indicator for primary mediastinal large B-cell lymphoma.

Due to the overlap of histological and molecular features of primary mediastinal large B-cell lymphoma (PMBL) with other lymphomas and its low incidence, the diagnosis and prognostic assessment of PMBL pose certain challenges. This study included 51 PMBL and 375 diffuse large B-cell lymphoma, not otherwise specified (DLBCL-NOS) from the GEO database and 65 PMBL and 117 DLBCL-NOS from a single center. At the transcriptional and protein levels, RHOF expression in PMBL was significantly higher than in DLBCL-NOS (P < 0.001). ROC curve analysis suggested that high RHOF expression had a high discriminative diagnostic ability for PMBL and DLBCL-NOS (transcriptional level, AUC = 0.913-0.940; protein level, AUC = 0.878). Comparing RHOF with commonly used PMBL diagnostic markers CD23, CD30, and PD-L1, it was found that high RHOF expression is a more useful diagnostic marker for PMBL (AUC (RHOF) = 0.878 > AUC (CD23) = 0.818 > AUC (CD30) = 0.756 > AUC (PD-L1) = 0.590). The diagnostic model based on CD23, CD30, and RHOF exhibits higher sensitivity for the diagnosis of PMBL than any of the individual markers mentioned above. Concerning prognosis, high RHOF transcriptional expression was significantly associated with poorer overall survival (OS) in PMBL (P = 0.00037), while high RHOF protein expression was significantly associated with poorer OS and progression-free survival (PFS) in PMBL (P = 0.034; P = 0.034). This study indicates that high RHOF expression in PMBL is closely associated with the diagnosis, prognosis, and clinical pathological features of the disease. High RHOF expression demonstrates a superior diagnostic ability in distinguishing PMBL from DLBCL-NOS compared to existing markers. Furthermore, research on RHOF expression in PMBL holds promise for providing new targets and insights for prognosis assessment and treatment of PMBL.

Customer Churn Prediction Approach Based on LLM Embeddings and Logistic Regression

Nowadays, predicting customer churn is essential for the success of any company. Loyal customers generate continuous revenue streams, resulting in long-term success and growth. Moreover, companies are increasingly prioritizing the retention of existing customers due to the higher costs associated with attracting new ones. Consequently, there has been a growing demand for advanced methods aimed at enhancing customer loyalty and satisfaction, as well as predicting churners. In our work, we focused on building a robust churn prediction model for the telecommunications industry based on large embeddings from large language models and logistic regression to accurately identify churners. We conducted extensive experiments using a range of embedding techniques, including OpenAI Text-embedding, Google Gemini Text Embedding, bidirectional encoder representations from transformers (BERT), Sentence-Transformers, Sent2vec, and Doc2vec, to extract meaningful features. Additionally, we tested various classifiers, including logistic regression, support vector machine, random forest, K-nearest neighbors, multilayer perceptron, naive Bayes, decision tree, and zero-shot classification, to build a robust model capable of making accurate predictions. The best-performing model in our experiments is the logistic regression classifier, which we trained using the extracted feature from the OpenAI Text-embedding-ada-002 model, achieving an accuracy of 89%. The proposed model demonstrates a high discriminative ability between churning and loyal customers.

Predictive Factors for Major Bleeding in Patients Undergoing Percutaneous Nephrolithotomy: A Clinical Prediction Study.

To evaluate major bleeding risk factors in percutaneous nephrolithotomy (PCNL) for upper urinary tract calculi and validate a prediction model. Analytical study. Place and Duration of the Study: The First Affiliated Hospital of Wannan Medical College, Wuhu, China, from January 2019 to August 2023. Major bleeding was defined as a decrease in haemoglobin of ≥20 g/L compared to preoperative levels. A retrospective analysis of 468 PCNL patients identified risk factors for major bleeding using univariate, LASSO, and logistic regression analyses. Nomogram models were developed using R software, with ROC and calibration plots assessing the model's accuracy. The bootstrap method provided internal validation, and DCA evaluated clinical utility. Independent risk factors included diabetes (OR = 4.17), staghorn calculi (OR = 3.41), operative duration (OR = 1.01), and staged surgery (OR = 2.75). The model showed high discriminative ability (C-statistic: 0.783) and alignment with observed outcomes. Internal validation confirmed robustness (C-statistic: 0.728). The predictive model for major bleeding during and after PCNL, focusing on diabetes, staghorn calculi, operative duration, and staged surgery, is highly accurate, aiding in the PCNL risk assessment. Upper urinary tract calculi, Percutaneous nephrolithotomy, Major bleeding, Risk factors, Prediction model.

Identification of Salient Brain Regions for Anxiety Disorders Using Nonlinear EEG Feature Analysis.

In this paper, we present a novel approach for identifying salient brain regions and interpreting the ability of nonlinear EEG features to discriminate between anxiety disorders and healthy controls. The proposed method involves the integration of advanced EEG preprocessing and artefact correction, nonlinear feature extraction using conditional permutation entropy, and interpretable machine learning to identify relevant electrodes. The extracted nonlinear features show statistically significant differences between classes, demonstrating high discriminative ability. The discriminative ability was confirmed with T-tests (p = 1.05e-10) and Mann-Whitney U tests (p = 2.65e-11), demonstrating robust statistical significance. Classification results support these findings and guide the identification of relevant electrodes, enhancing the interpretability of the discriminative features. This approach highlights potential brain regions critical for anxiety disorder diagnosis, paving the way for more targeted interventions and improved clinical outcomes.

A generalised computer vision model for improved glaucoma screening using fundus images.

Worldwide, glaucoma is a leading cause of irreversible blindness. Timely detection is paramount yet challenging, particularly in resource-limited settings. A novel, computer vision-based model for glaucoma screening using fundus images could enhance early and accurate disease detection. To develop and validate a generalised deep-learning-based algorithm for screening glaucoma using fundus image. The glaucomatous fundus data were collected from 20 publicly accessible databases worldwide, resulting in 18,468 images from multiple clinical settings, of which 10,900 were classified as healthy and 7568 as glaucoma. All the data were evaluated and downsized to fit the model's input requirements. The potential model was selected from 20 pre-trained models and trained on the whole dataset except Drishti-GS. The best-performing model was further trained to classify healthy and glaucomatous fundus images using Fastai and PyTorch libraries. The model's performance was compared against the actual class using the area under the receiver operating characteristic (AUROC), sensitivity, specificity, accuracy, precision and the F1-score. The high discriminative ability of the best-performing model was evaluated on a dataset comprising 1364 glaucomatous discs and 2047 healthy discs. The model reflected robust performance metrics, with an AUROC of 0.9920 (95% CI: 0.9920-0.9921) for both the glaucoma and healthy classes. The sensitivity, specificity, accuracy, precision, recall and F1-scores were consistently higher than 0.9530 for both classes. The model performed well on an external validation set of the Drishti-GS dataset, with an AUROC of 0.8751 and an accuracy of 0.8713. This study demonstrated the high efficacy of our classification model in distinguishing between glaucomatous and healthy discs. However, the model's accuracy slightly dropped when evaluated on unseen data, indicating potential inconsistencies among the datasets-the model needs to be refined and validated on larger, more diverse datasets to ensure reliability and generalisability. Despite this, our model can be utilised for screening glaucoma at the population level.

Predictive ability of anthropometric indices for risk of developing metabolic syndrome: a cross-sectional study.

To determine the discriminatory ability of different anthropometric indicators of body fat percentage for diagnosing metabolic syndrome (MetS) in a Peruvian sample. This was a cross-sectional, non-experimental, diagnostic accuracy study. Anthropometric and biochemical data for 948 participants were analyzed. Waist circumference (WC), body mass index, relative fat mass (RFM), conicity index, body roundness index (BRI), waist-to-height ratio (WHtR), and A Body Shape Index were assessed for their MetS discriminatory ability. The National Cholesterol Education Program's Adult Treatment Panel III criteria were used to diagnose MetS. Receiver operating characteristic curves and area under the curve (AUC) were used to determine the predictive power of each anthropometric measurement to diagnose MetS. In both sexes, RFM, BRI, and WHtR showed the same predictive ability to diagnose MetS. In women, indicators incorporating WC showed high discriminatory ability: RFM, BRI, and WHtR (all AUC: 0.869, 95% confidence interval [CI]: 0.828-0.910). In men, WC had the highest AUC (0.829, 95% CI: 0.793-0.866). In both sexes, RFM, WC, BRI, and WHtR were the best predictors of MetS diagnosis. This is the first study to identify RFM as a potentially useful clinical predictor of MetS in a Peruvian sample of educational workers.

Development of a Short-Form Hwa-Byung Symptom Scale Using Machine Learning Approaches.

Background/Objectives: Hwa-byung (HB), also known as "anger syndrome" or "fire illness", is a culture-bound syndrome primarily observed among Koreans. This study aims to develop a short-form version of the HB symptom scale using machine learning approaches. Methods: Utilizing exploratory factor analysis (EFA) and various machine learning techniques (i.e., XGBoost, Logistic Regression, Random Forest, Support Vector Machine, Decision Tree, and Multi-Layer Perceptron), we sought to create an efficient HB assessment tool. A survey was conducted on 500 Korean adults using the original 15-item HB symptom scale. Results: The EFA revealed two distinct factors: psychological symptoms and somatic manifestations of HB. Statistical testing showed no significant differences between using different numbers of items per factor (ANOVA: F = 0.8593, p = 0.5051), supporting a minimalist approach with one item per factor. The resulting two-item short-form scale (Q3 and Q10) demonstrated high predictive power for the presence of HB. Multiple machine learning models achieved a consistent accuracy (90.00% for most models) with high discriminative ability (AUC = 0.9436-0.9579), with the Multi-Layer Perceptron showing the highest performance (AUC = 0.9579). The models showed balanced performance in identifying both HB and non-HB cases, with precision and recall values consistently around 0.90. Conclusions: The findings of this study highlighted the effectiveness of integrating EFA and artificial intelligence via machine learning in developing practical assessment tools. This study contributes to advancing methodological approaches for scale development and offers a model for creating efficient assessments of Korean medicine.

Clinical validated risk prediction model for development of heart failure after contemporary breast cancer treatment

Abstract Background Patients receiving breast cancer (BC) treatment are at risk for heart failure and cardiomyopathy (HF/CM). European Society of Cardiology (ESC) cardio-oncology guidelines recommend baseline cardiovascular (CV) assessment, however, there is limited data about cardiotoxicity risk specific to patients with BC. Our aim was to develop and validate model for prediction of HF/CM in women receiving contemporary treatment for invasive early-stage BC. Methods We assembled a cohort women diagnosed with Stage I-III BC from 2008-2020 and followed through 2021 in a large health care plan. Women age &amp;gt;80, with history of HF/CM, and women who received both anthracyclines and trastuzumab were excluded, leaving N=26,044 for analysis. Study cohort was randomly split into derivation (60%) and validation (40%) datasets. Elastic-net penalized Cox proportional hazard model was created using the derivation dataset to select risk factors and to calculate the panelized coefficient which defined the HF/CM risk score. Risk score system was assessed by Hosmer-Lemeshow goodness-of-fit test and area under the ROC curve (AUC). Event rates of &amp;lt;5% constituted low risk; 5-14% moderate; and &amp;gt;15% high risk category. Incident HF/CM events were examined using Kaplan-Meier approach in derivation and validation datasets. Results HF/CM risk score had high discrimination ability and sufficiently good model of fit regarding HF/CM events (P value=0.163 and 0.667 from Hosmer–Lemeshow test;AUC 0.751 and 0.764, in derivation and validation sets, respectively). There were 10% of women in the high risk; 30% in moderate; and 60% in low-risk group. Variables associated with the higher HF/CM risk score included age, receipt of anthracycline-based chemotherapy or anti-HER2 therapy, presence of hypertension, diabetes, or history of other CV conditions at baseline. The score pattern showed major effect of age, with anthracycline and anti-HER2 therapy increasing the risk across all age groups (Figure 1). Kaplan-Meier analysis of incident HF/CM over 14 years after BC diagnosis showed significantly lower number of HF/CM events in low risk compared to moderate and high-risk score groups (p&amp;lt;0.0001, Figure 2). Conclusion Our robust risk prediction model for HF/CM among women with early-stage BC provides a new tool to identify women at higher CV risk and inform cardiac function monitoring during and after BC treatment. Our findings may guide further validation studies and build evidence for the cardiotoxicity risk stratification in patients with BC.Risk Score for HF/CM by Age/ChemoTxK-M curves of freedom from HF/CM

Evaluation of naples prognostic score to predict long-term mortality in patients with pulmonary embolism

Abstract Background/Introduction APE mortality rates are still not satisfactory despite new diagnosis and treatment methods (1). Thus, risk classification is crucial due to the wide range of clinical presentations. Several risk stratifications have been developed such as simplified Pulmonary Embolism Severity Index (sPESI) (2). Nonetheless, there remains a need for an optimal indicator that can be conveniently measured with a high degree of precision to predict clinical outcomes. Naples prognostic score (NPS) is a newly defined index that is developed to determine the prognosis of cancer patients and reflects the inflammatory and nutritional status of the patients (3). Purpose The aim of our study was to determine the long-term prognostic value of NPS in APE patients. Methods Two hundred ninety-three patients diagnosed with APE between November 2016 and February 2022 were included in the study. NPS consists of 4 parameters: serum albumin, total cholesterol (TC) concentration, neutrophil-to-lymphocyte ratio (NLR) and lymphocyte-to-monocyte ratio (LMR). Naples scores of all patients were calculated and the patients were divided into 2 groups according to their NPS and their long-term mortality was compared. The primary endpoint of the study was long-term mortality. Results The long-term mortality was observed in 38 patients out of 293 patients in the mean follow-up of 24 (16-42) months. In the low-Naples risk group (group 1), there were 215 patients, while the high-Naples risk group (group 2) had 78 patients. Multivariate analysis showed that NPS as a categorical parameter (HR: 3.458, 95%CI:1.734-6.896, p&amp;lt;0.001), NPS as a numerical parameter, (HR:1.651, 95%CI:1.217-2.241, p=0.001) and simplified pulmonary embolism severity index (sPESI) (HR:1.887, 95%CI:1.223-2.911), p=0.004) score were independent predictors of long-term mortality. The receiver operating characteristic curve analysis showed that the model 2 with NPS as continuous had higher discriminative ability than the baseline model for detecting patients with mortality (Area under curve (AUC) values = 0.791 vs. 0.723, respectively, p=0.04) (Figure 1A). The long-term predictive capability of NPS was non-inferior than the sPESI score (Figure 1B). Conclusions The current study highlights that NPS, which reflects systemic inflammation and nutritional status may have potential to predict long-term mortality in APE patients. To our knowledge, this is the first study to show the relationship between long-term mortality and NPS in APE patients.

Identifying paediatric patients at risk of severe hearing impairment after treatment for malignancies of the H&N/CNS with proton therapy

Background and purposeA risk calculation model was presented in 2021 by Keilty et al. for determining the likelihood of severe hearing impairment (HI) for paediatric patients treated with photon radiation therapy. This study aimed to validate their risk-prediction model for our cohort of paediatric patients treated with proton therapy (PT) for malignancies of the head and neck (H&N) or central nervous system (CNS). Materials and methodsThis was a single-institution study which extracted data on all patients aged ≤ 18 years treated with PT between Feb 2010 – Feb 2022 for malignancies of the H&N/CNS. The factors required for input into the Keilty model were extracted: age at PT, time since end of PT, mean cochlea dose, and platinum chemotherapy doses. Validation was performed using the statistical software R v 4.3.1, which analysed event discrimination and model calibration. Results587 patients met the criteria. Validation of the model demonstrated excellent discriminative ability, with an “optimal” cut-off value of 16% at a specificity and sensitivity of 82%. However, model calibration was less satisfactory, indicating an overestimation of risk of severe hearing loss (HI) by the model as compared to clinically observed events in our cohort, possibly linked to differences in event scoring between the model developers and this study, and short follow-up time in this study. ConclusionThe published (photon-based) model of Keilty et al. was validated in a PT context, demonstrating a high discriminative ability to determine patients at high risk versus low risk for severe HI. However the overall observed risk was lower than model predictions.

Bioinformatics investigation of the prognostic value and mechanistic role of CD9 in glioma

In recent years, CD9 has been extensively studied as a potential biomarker for cancer. However, the biological role of CD9 in gliomas remains unclear. This study investigates the function of CD9 in gliomas and its molecular mechanisms. Utilizing pan-cancer analysis with TCGA, CGGA, and GEO databases, differential expression of CD9 was observed in 11 tumor types within the TCGA cohort, and it was associated with patient survival rates. Analysis of the CGGA glioma database revealed that patients with high CD9 expression had lower survival rates. The area under the ROC curve (AUC) for GSE16011 was greater than 0.7, indicating a high discriminative ability. Through gene set enrichment analysis (GSEA), immune-related analysis, and CD9 mutation detection, CD9 was found to have the strongest correlation with neutrophil involvement (cor = 0.30, P < 0.05), and the high CD9 expression group exhibited higher rejection responses and TIDE scores, suggesting a lower likelihood of successful immunotherapy. The high CD9 expression group was more sensitive to 81 drugs, indicating potential therapeutic effects for gliomas. Furthermore, overexpression of CD9 in gliomas may be associated with gene mutations. Down-regulation or up-regulation of CD9 expression in the glioblastoma cell line LN229 showed that CD9 could positively regulate the migratory ability of LN229 cells. Further, several marker genes, such as VEGFR-2, TGF-β1, CASP1 and PI3K, were down regulated in CD9 knockdown cell lines and up regulated in CD9 overexpression cell lines, compared with control cell line. This study preliminarily explores the role of CD9 in gliomas and its prognostic value, providing new insights for personalized treatment strategies in glioma therapy.

Predicting poststroke cognitive impairment after acute ischemic stroke based on admission characteristics

ObjectiveThis study aimed to develop a robust clinical prediction model for Poststroke cognitive impairment (PSCI) within 6 months following acute ischemic stroke (AIS) and subsequently validate its effectiveness. MethodsA total of 386 AIS patients were divided into the PSCI group (174 cases) and the cognitively normal (CN) group (212 cases) based on the occurrence of PSCI. These patients were further categorized into two cohorts: 270 AIS patients in the training set, 116 AIS patients in the validation set. Multifactor logistic regression analysis was performed to identify independent predictors, which were then included in the prediction model for further analysis and validation. The performance of the prediction model was evaluated using the area under the receiver operating characteristic curve (AUC-ROC), calibration plots analyses to assess discrimination, calibration ability, respectively. ResultsBased on the selected variables (smoking, alcohol consumption, female gender, low education level, NIHSS score at admission, stroke progression, high systolic blood pressure, diabetes, atrial fibrillation, coronary heart disease, low-density lipoprotein cholesterol, β2-microglobulin, and Lp-PLA2), a clinical prediction model for the occurrence of PSCI within 6 months in AIS patients was constructed. The AUC-ROC of the model was 0.862, 0.806 in the training, validation sets, respectively. Calibration curve analyses and Hosmer-Lemeshow goodness-of-fit tests, along with other validation metrics, further demonstrated the model's good predictive performance. ConclusionThe model exhibits high discriminative ability for PSCI and has substantial guiding value for clinical decision-making. However, further optimization of the model is required with multicenter data to enhance its robustness and applicability.

Construction of a Risk Prediction Model for Ureteral Stricture after Ureteroscopic Holmium Laser Lithotripsy.

Introduction: To analyze the influencing factors of ureteral stenosis after ureteroscopic holmium laser lithotripsy. Methods: The clinical data of 427 patients treated with ureteroscopic holmium laser lithotripsy were selected, and the patients were divided into two groups based on the presence or absence of ureteral stenosis after the operation. Univariate and multivariate logistic regression were used to analyze the independent risk factors for postoperative ureteral stenosis, and R software and regression coefficients were used to construct a predictive model. Results: After a 1-year follow-up of 427 patients, 28 patients (6.56%) developed ureteral stenosis; univariate analysis showed that the occurrence of ureteral stenosis after subureteral holmium laser lithotripsy was related to stone diameter, stone incarceration, degree of hydronephrosis, holmium laser injury of mucosa, and operation time (p < 0.05); further logistic regression analysis showed that a large stone diameter, stone incarceration, and moderate to severe hydronephrosis were independent risk factors for ureteral stenosis after ureteroscopic holmium laser lithotripsy (p < 0.05); According to H-L deviation degree and area under receiver operating characteristic curve test, the results show that the model has high accuracy (χ2 = 2.475, p = 0.613) and differentiation (0.875 [95% confidence interval or CI: 0.817-0.919]), and the external verification of the nomogram prediction model was carried out by the verification group. The results showed that the prediction probability of the calibration curve was close to the actual probability and had a good consistency (area under the curve: 0.873 [95 CI: 0.822-0.914]). Conclusion: The established nomogram model exhibits high accuracy and discriminative ability. It can effectively identify high-risk groups, enabling timely prevention of ureteral stenosis and minimizing the risk of postoperative ureteral stenosis.

An analysis of the clinical significance of the TKI-resistant gene ZNF687 for hepatocellular carcinoma patients.

Novel treatments such as monotherapy and combined immunotherapy significantly extend overall survival (OS) for hepatocellular carcinoma (HCC) patients, but HCC is susceptible to treatment resistance during long-term therapy. The resistance mechanism to targeted drugs in HCC remains ambiguous, making research on HCC drug resistance targets crucial for the development of precision medicine. To investigate the transcriptional features, biological functions and potential clinical value of the tyrosine kinase inhibitor (TKI)-resistant gene ZNF687 in HCC. The TKI-resistant genes of HCC were identified using clustered regularly interspaced short palindromic repeats (CRISPR) in vitro screening. Then, the dependence of HCC cell lines on ZNF687 was investigated in silico. We collected global mRNA datasets of HCC tissue, integrated the mRNA expression characteristics of ZNF687 in HCC and explored the impact of ZNF687 on HCC patient prognoses using the Kaplan-Meier method (in silico). The Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways analyses were then conducted, and a connectivity map and molecular docking technology were applied to find the underlying agent opposing ZNF687. In vitro, the guide RNA corresponding to ZNF687 was weakly detected in HCC cells, and ZNF687 deficiency was found to inhibit growth in HCC cell lines. ZNF687 mRNA was overexpressed and had a high discriminatory ability for HCC in 2,975 HCC samples, contrasting with 2,340 non-HCC samples. Moreover, an excessive ZNF687 transcript level was related to a worse overall survival (OS) prognosis. Histone modification, spliceosome, transcription coregulator activity, and nucleocytoplasmic transport were the most significant pathways for ZNF687 differential-related gene enrichment. Chaetocin was found to be a candidate compound and presented a strong affinity to ZNF687. ZNF687 represents a TKI-resistant and growth-dependent gene for HCC, the overexpression of which indicates poor OS for HCC patients. Additionally, ZNF687 is expected to be a druggable target for overcoming TKI resistance, and chaetocin may be a candidate therapeutic compound for ZNF687.

Development and validation of a hierarchical approach for lymphoma classification using immunohistochemical markers.

Accurate lymphoma classification is critical for effective treatment and immunohistochemistry is a cost-effective and time-saving approach. Although several machine learning algorithms showed effective results, they focused on a specific task of classification but not the whole classification workflow, thus impractical to be applied in clinical settings. Thus, we aim to develop an effective and economic machine learning-assisted system that can streamline the lymphoma differential diagnostic workflow using EBER insitu hybridization and immunohistochemical markers. We included pathological reports diagnosed as lymphomas from two cancer centers (Sun Yat-sen University Cancer Center and Peking University Cancer Hospital & Institute). We proposed a hierarchical approach that mimicked the human diagnostic process and employed simplified panels of markers to perform a series of interpretable classification. The diagnostic accuracy for lymphoma pathological subtypes and the markers saving ratio were investigated in both temporal independent population and external medical center. A total of 14,927 patients and corresponding immunohistochemical results from two cancer centers were included. The proposed system had high discriminative ability for differentiating lymphoma pathological subtypes (measured by mean AUC in three validation cohorts, non-Hodgkin and Hodgkin lymphoma: 0.959; non-Hodgkin subtypes: 0.983; B-lymphoma subtypes: 0.868; T-lymphoma subtypes: 0.962; DLBCL subtypes: 0.957). In addition, the system's well selected characteristics can contribute to the development of agreement on panels of markers for differential diagnosis and help minimize cost of immunohistochemical marker techniques (measured by marker saving ratio compared to real clinical settings, internal primary-stage cohort: 16.45% saved, p < 0.001; internal later-stage cohort: 21.73% saved, p < 0.001; external cohort: 3.67% saved, p < 0.001). Machine learning-based hierarchical system using EBER insitu hybridization and IHC markers was developed, which could streamline the workflow by sequentially determining each lymphoma pathological subtype. The proposed system proved to be effective and cost-saving in independent and external validation, thus could be adopted affordably in future clinical practice.

Enhancing Target Tracking: A Novel Grid-Based Beetle Antennae Search Algorithm and Confusion-Aware Detection.

Unmanned aerial vehicle target tracking is a complex task that encounters challenges in scenarios involving limited computing resources, real-time requirements, and target confusion. This research builds on previous work and addresses challenges by proposing a grid-based beetle antennae search algorithm and designing a lightweight multi-target detection and positioning method, which integrates interference-sensing mechanisms and depth information. First, the grid-based beetle antennae search algorithm's rapid convergence advantage is combined with a secondary search and rollback mechanism, enhancing its search efficiency and ability to escape local extreme areas. Then, the You Only Look Once (version 8) model is employed for target detection, while corner detection, feature point extraction, and dictionary matching introduce a confusion-aware mechanism. This mechanism effectively distinguishes potentially confusing targets within the field of view, enhancing the system's robustness. Finally, the depth-based localization of the target is performed. To verify the performance of the proposed approach, a series of experiments were conducted on the grid-based beetle antennae search algorithm. Comparisons with four mainstream intelligent search algorithms are provided, with the results showing that the grid-based beetle antennae search algorithm excels in the number of iterations to convergence, path length, and convergence speed. When the algorithm faces non-local extreme-value-area environments, the speed is increased by more than 89%. In comparison with previous work, the algorithm speed is increased by more than 233%. Performance tests on the confusion-aware mechanism by using a self-made interference dataset demonstrate the model's high discriminative ability. The results also indicate that the model meets the real-time requirements.

Prognostic value of nutrition for contrast-induced nephropathy in patients undergoing peripheral vascular intervention.

Background: The objective was to examine the predictive value of malnutrition, assessed via the Controlling Nutritional status (CONUT) and Prognostic Nutrition Index (PNI) scores, in the development of contrast-associated acute kidney injury (CA-AKI) following peripheral vascular intervention (PVI).Methods: This retrospective cross-sectional observational study included the enrollment of 243 consecutive patients who underwent PVI. Patients were categorized into two groups based on the occurrence of CA-AKI.Results: Patients with CA-AKI had lower PNI scores and the PNI score was an independent predictor of CA-AKI development (Odds Ratio: 0.518, 95% CI: 2.295-0.908, p=0.021). Nomogram had higher discriminative ability than both PNI and CONUT scores and discriminative abilities were similar for PNI and CONUT scores.Conclusion: Malnutrition, as identified by the CONUT and PNI, was found to be associated with a high risk of CA-AKI development following PVI.

Metabolomic profiles differentiate between porto-sinusoidal vascular disorder, cirrhosis, and healthy individuals

Background & AimsPorto-sinusoidal vascular disorder (PSVD) is a rare and diagnostically challenging vascular liver disease. This study aimed to identify distinct metabolomic signatures in patients with PSVD, cirrhosis, and healthy volunteers (HV) to facilitate non-invasive diagnosis and elucidate perturbed metabolic pathways. MethodsSerum samples from 20 HV and patients with histologically confirmed PSVD or cirrhosis were analyzed. Metabolites were measured using liquid chromatography-mass spectrometry (LC-MS). Differential abundance was evaluated with Limma’s moderated t-statistics. Artificial neural network (ANN) and support vector machine (SVM) models were developed to classify PSVD against cirrhosis or HV metabolomic profiles. An independent cohort was used for validation. ResultsA total of 283 metabolites were included for downstream analysis. Clustering effectively separated PSVD metabolomes from HV, although a subset of PSVD patients (n=5, 25%) overlapped with cirrhosis. Differential testing revealed significant PSVD-linked metabolic perturbations, including taurocholic and adipic acids, distinguishing PSVD from both HV and cirrhosis. Alterations in pyrimidine, glycine, serine, and threonine pathways were exclusively associated with PSVD. Machine learning models utilizing selected metabolic signatures reliably differentiated PSVD from HV or cirrhosis using only 4 to 6 metabolites. Validation in an independent cohort demonstrated the high discriminative ability of taurocholic acid (AUROC 0.899) for PSVD vs HV and the taurocholic acid/aspartic acid ratio (AUROC 0.720) for PSVD vs cirrhosis. ConclusionsHigh-throughput metabolomics enabled the identification of distinct metabolic profiles for differentiating PSVD, cirrhosis, and healthy individuals. Unique alterations in the glycine, serine, and threonine pathways suggest their potential involvement in PSVD pathogenesis. Impact And ImplicationsPorto-sinusoidal vascular disorder (PSVD) is a vascular liver disease that can lead to pre-sinusoidal portal hypertension in the absence of cirrhosis, with poorly understood pathophysiology and no established treatment. Our study demonstrates that analyzing the serum metabolome could reveal distinct metabolic signatures in PSVD patients, including alterations in the pyrimidine, glycine, serine and threonine pathways and potentially shedding light on the disease's underlying pathways. These findings hold potential for earlier and non-invasive diagnosis of PSVD, potentially reducing reliance on invasive procedures like liver biopsy and guiding diagnostic pathways.

Predicting Long-Term Clinical Outcomes of Patients With Recurrent Pericarditis

BackgroundRecurrent pericarditis (RP) is a complex condition associated with significant morbidity. Prior studies have evaluated which variables are associated with clinical remission. However, there is currently no established risk-stratification model for predicting outcomes in these patients. ObjectivesWe developed a risk stratification model that can predict long-term outcomes in patients with RP and enable identification of patients with characteristics that portend poor outcomes. MethodsWe retrospectively studied a total of 365 consecutive patients with RP from 2012 to 2019. The primary outcome was clinical remission (CR), defined as cessation of all anti-inflammatory therapy with complete resolution of symptoms. Five machine learning survival models were used to calculate the likelihood of CR within 5 years and stratify patients into high-risk, intermediate-risk, and low-risk groups. ResultsAmong the cohort, the mean age was 46 ± 15 years, and 205 (56%) were women. CR was achieved in 118 (32%) patients. The final model included steroid dependency, total number of recurrences, pericardial late gadolinium enhancement, age, etiology, sex, ejection fraction, and heart rate as the most important parameters. The model predicted the outcome with a C-index of 0.800 on the test set and exhibited a significant ability in stratification of patients into low-risk, intermediate-risk, and high-risk groups (log-rank test; P < 0.0001). ConclusionsWe developed a novel risk-stratification model for predicting CR in RP. Our model can also aid in stratifying patients, with high discriminative ability. The use of an explainable machine learning model can aid physicians in making individualized treatment decision in RP patients.

Predictors of 24-month onset of macular fibrosis in type 3 macular neovascularisation

AimsTo explore prognostic multimarker models for progression to macular fibrosis (MF) over 24 months specific to type 3 macular neovascularisation (T3 MNV).MethodsThis retrospective, exploratory, single-centre, cohort study comprised 65 eyes...